Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/aejpol-workflow
Use when deciding which aejpol-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for an AEJ: Economic Policy manuscript. Routes — it does not replace — the specialized skills.
Passed 0 of 21 test cases with the skill, and 21 of 21 without it.
and 9 more in the full report
12 fixed6 passed either way2 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our baseline policy elasticity changes significantly when we drop cluster controls or change sample windows. Which workflow module is designed to stress-test specification stability and threats to validity?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies `aejpol-robustness` as the required module. | Missed | Passed |
The instructions your model reads when the skill loads.
This is the router. It tells you which aejpol- skill to use at the current stage* of a manuscript aimed at the American Economic Journal: Economic Policy (AEJ: Policy) — the American Economic Association's quarterly journal for the economic analysis OF policy. AEJ: Policy rewards a paper built around a clear policy question whose answer carries a welfare, cost-benefit, or distributional implication, identified credibly (quasi-experimental / RCT / applied theory) and reproducible to AEA standards. The policy question and its counterfactual are the through-line of every skill below.
Default assumption: unless the user says otherwise, treat the target as AEJ: Policy. Operational tells that you are at AEJ: Policy and not a sibling: review is single-blind through the AEA submission system (the manuscript carries the title/byline/affiliations); JEL codes are required; the AEA Data and Code Availability Policy and the AEA Data Editor run a pre-publication reproducibility check on a deposit in the AEA Data and Code Repository (openICPSR); the bar is broad policy interest + credible causal evidence + a welfare/cost-benefit reading, not a field-public-finance bar (J. Public Economics) or an identification-for-its-own-sake bar (AEJ: Applied). Re-verify volatile specifics (submission fee, editors) on the official AEA pages — official AEA pages checked 2026-06-20.
| Current symptom | Next skill |
|---|---|
| No sharp policy question, or fit vs. JPubE / AEJ:Applied / AER unclear | aejpol-topic-selection |
| Contribution vs. the policy-evaluation literature is fuzzy or undersold | aejpol-literature-positioning |
| Causal design (DID / IV / RDD / RCT) for the policy's effect is shaky | aejpol-identification |
| Need a model/welfare framework to read estimates as a policy effect | aejpol-theory-model |
| Estimate stability, sensitivity, and threats need stress-testing | aejpol-robustness |
| Exhibits are dense; significance asterisks still present | aejpol-tables-figures |
| Prose buries the policy takeaway; abstract/intro do not land | aejpol-writing-style |
| Data/code deposit, README, AEA Data Editor prep, restricted-data path | aejpol-replication-package |
| Want to anticipate the referees' objections before submitting | aejpol-referee-strategy |
| Ready to submit via the AEA system; need a preflight | aejpol-submission |
| Received an R&R; need a response-letter strategy | aejpol-rebuttal |
aejpol-topic-selection — lock the policy question + the welfare/cost-benefit stakeaejpol-literature-positioning — stake the contribution vs. the policy-evaluation frontieraejpol-identification — credible quasi-experimental / RCT evaluation of the policyaejpol-theory-model — the framework that maps estimates to a welfare/policy objectaejpol-robustness — sensitivity, threats, specification stabilityaejpol-tables-figures — exhibits without significance asterisks; a policy-relevant headline exhibitaejpol-writing-style — translate estimates into a clear policy takeaway (abstract + intro last)test cases passed, vs 21 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.